Smart plugs and device detection

As both a Hue and HS110 smartplug user, I’ll give my perspective. The beauty of Hue and smartplugs is that they result in more known devices in your house, and less power ending up in either Always On or Other categories. The HS110 also helps with learning the device it is attached to, but not device on outlet strips, since the smartplug supplies Sense with ‘ground truth’ for that specific device. ‘Ground truth’ is a key ingredient in the machine learning training process.

I don’t think having things identified via smartplug or Hue helps focus Sense on ‘other things’ within your house. It’s not like the Sense algorithms can subtract off found devices from the waveform. Training is more about Sense learning how to focus in on very selective aspects of the incoming waveforms, not ‘elimination’. But you do benefit from others who use smartplugs and supply ground truth for devices you have in your house, that you may or may not have used a smartplug on.

I just learned today that if you have a Hue device plugged into a smart plug, you can’t merge them. I had logged a ticket because I got a new plug that I am using for my home theater, which has various things, plus the LG TV that had been detected, and a Hue bulb. But I couldn’t add the Hue bulb to the smart plug so it is being double counted. Support says they are going to fix it, just wanted to pass that along.

1 Like

Is there a topic anywhere that explains why sense has such a difficult time detecting a device that we do clearly see and can identify? I’d like to understand why when I see things like my floor heater come on and recognize it immediately and it follows the same pattern that sense doesn’t see it.

I don’t think there is a good explanation per se, but I think some of the Sense technical blogs are helpful in understanding how the Sense system works. But the best way to understand why Sense isn’t perceiving some device waveforms the way you see them is to look at the waveforms from the same perspective Sense sees them - mostly via sub-second windows.

Sense made an early tradeoff to focus on near realtime detection so bubbles show up almost immediately after the device comes on, but means that they are only allowed a small window of waveform to do the identification. All of the stuff you see in the Power Meter is far outside that window (1/2 second resolution). Sense has said they are working on wider window identifications (post-detection, where the device is detected after a significant portion of the waveform has gone by, like us humans do), but typically in the context of specific devices like EV chargers. And they have plenty of EV detectors in action.

But I think the toughest part of their work is AUTOMATICALLY developing/installing detections that work consistently and automatically for every house. You might be able to spot devices in your home most of the time, but doing the same in 100 other homes with different conditions would probably be very challenging.

2 Likes

One of the AskSense question touched on this, so keep watching. I should be able to get that video up soon…just a tad more editing to do.

4 Likes

@samwooly1,

Not sure if you had a chance to watch this video, but it also gives some good insights from the Sense experts.

3 Likes

Oh yes, Ryan told me something was coming a couple days ago and when I saw that post this morning I went and watched.
When I was referring to George, that was him In the video.

1 Like

One of the biggest benefits of the smart plug would seem to be allowing the users to label the device that’s creating the specific electrical draw. It would seem that having a pre-classified data electrical load would make it easier to identify similar devices? Instead of having to use ML to infer what a particular device might be, you would have a pre identified load that should be able to be used as a baseline for identifying similar loads, no?

If you’ve already profiled the electrical draw of the smart plugs (since it’s not zero) you shouldn’t in theory be able to cancel out the draw from the smart plug itself, record the draw from the device with the label and then use that as the identifying mechanism. Sure, you might have to leave the smart plug in place for X timeframe ( a month maybe?) to be able to learn enough about the patterns of that particular device (gather enough data sample) to be able to identify it when the smart plug is removed.

Using this methodology, you should also be able to start getting a better handle on always on devices as they would actually be labeled by the customer.

I’d love to run around my house moving smart plugs for the next year to be able to help teach Sense to better identify devices in my environment. I’m not so enthused about having to buy a smart plug for every device that I would like to have detected properly. Especially when I’m a Apple Homekit user and the TP link option isn’t even compatible with my smart home system.

Hope this helps!

Chris

Hey Chris,
The labeling you mention is exactly what what the sanest plugs are being used for now (T P Link). Say I plug a toaster into a HS110 and enter the label in correctly. Not only do I have that association but sense is using that on the backend for identification purposes. I also had thought about the moving around idea but was told by a user with a lot more knowledge that it would have to see hundreds to thousands of cycles to be helpful. So probably a few months at each location, still worth the trouble in my opinion because it will help future users.
Sorry if I missed anything.
Edit: just noticed that was meant for @RyanAtSense and thought it was for me, sorry about that.
Dan

Not really possible to “cancel out” a smartplug’s contribution to the whole house wave waveforms with such a huge disparity between sample resolutions - 1/2 second for Smartplug, 1 microsecond for Sense samples, plus variable latency of smartplugs. Best you can do is use the smartplugs for reinforcement learning.

I would definitely suggest checking out the smart plug FAQ and our blog post on the integration.

You can already label smart plugs and the data is proving incredibly beneficial to our data science team. We don’t yet have a mechanism in place for Sense to learn, in perpetuity, the device from the smart plug, but that’s something we’re working on. That’s mentioned in a bit more detail in the links above.

2 Likes

Ok. That makes sense regarding the differences in the units used for measurement. But the reinforcement learning portion should be possible and useful. The biggest user-benefit I’m looking for is the ability to buy a few plugs, use them to train the system with a user supplied label for a period of time ( a month? ) and then unplug the smart plug, connect the device back to the wall and re-implement the plug with the next unknown device in the line.

There was to be a balance between not having any ability too label our devices ( device plugged directly into the wall ) and having to buy a smart plug for every device we want to have detected properly.

As I went through my smart home journey, I’ve got smart plugs from various different vendors, Vocolinc, Koogeek, iDevices, iHome, Ikea, Aqara and more… I understand integrations are always a work in progress, but I’m not loving the idea that I would have to buy new Wemo or TPLink plugs and replace the ones I’ve already got.

Just hoping for something more. :slight_smile:

Christopher

1 Like

Can’t add to the Detection FAQ anymore, so I wanted to bring this suggestion back here. I’d be more than willing to vote with my wallet if Sense released a smartplug that operated as a remote unit who’s job was to report/detect only the specific device that was plugged into it. This should allow the users to label the plugged in device accurately, and also give the high speed sampling rate that Sense is using at the electrical panel to be able to capture the devices specific electrical personality and match it with the label.

Additional controls could also be a tag to mark the device as active/non-active ( just a user button that creates a tag at a specific time point in the data stream ) to help Sense understand when an always-on device like a TV/DVR etc… is really active vs. Sitting there passively sucking electricity.

Most importantly, The device would also have to be able to be moved around after a month or so and reusable throughout the house. The actual time it would need to learn a specific device would be, of course, based on the sense algorithm and might require more or less time depending on the device.

I would be more than happy to pay a premium for a smartplug that allowed sense to learn more and gave me the ability to help teach the system.

Thoughts?

Chris

2 Likes

This is what smart plugs are already doing for us, though the sampling rate isn’t as high. But you’re right, at this point it cannot be moved off of that device and still remember that detection. As noted in the linked posts above, that’s something we hope to implement in the future after we pull more data via these plugs.

But, already they’re allowing Sense to learn more and are giving you the ability to teach the system.The timescale is just not immediate.

4 Likes

AND, since many of the detect ion problems are with 220v devices, a module that can be wired into a 220v circuit (perhaps permanently) would be of huge value. There don’t seem to be any such devices on the market yet, but Sense, perhaps partnering with TPlink (who already has 220v capability, unfortunately packaged for EU plugs) could certainly benefit from such a product.

1 Like

Another thing I thought could be in sense future for 240 devices is just like other manufacturers have done, with CT’s for each load. Each 240 breaker that is. Could they create an interface or maybe through the Schneider partnership have made, an interface that wirelessly connects to home WiFi but is reading several 240 loads from separate CT’s for each? The servers then could do the work to integrate the information sent from the sense monitor to send back to our viewers.

1 Like

Hey @RyanAtSense,

Totally appreciate the response. If the plug doesn’t allow me to train sense and then move it around, it’s just not valuable to me. The implications being that I would have to buy a smart plug for a ton of devices in my house that I either don’t want or would have to replace smart plugs I already own without ecosystem compatibility. Not a compelling argument for me.

Hoping Sense comes up with a way to move plugs around soon. :slight_smile:

Christopher

2 Likes

I think Ryan has already part of your question - there is a future that includes what you are asking for. I do want to point out that building/selling a device with the same sampling resolution as the Sense monitor puts it into a very different cost category than the HS110 (200$ vs 15$).

The strategy I have taken with smartplugs is to buy enough for the interesting 120V plugin devices in my house that haven’t been detected, plus one roamer that I use as an enhanced Kill-A-Watt for investigating.

  • interesting means that they are not constant draw like virtually all of my networking gear.
  • and I have put HS110s on two identified devices as well, my furnaces, since the Hs110 reveals additional significant components beyond the detected blower.
  • I actually wasted a HS300 on my networking gear (modem, router, access point, main switch, cable amps) since all of those are essentially constant. Just as helpful to put them all on power strip with an HS110.
2 Likes

Sorry if you are just talking to Ryan Chris but can I share a thought?
I’m using integrated plugs and here is what I think.
I take the plug and use it for a device so I can use it with Sense to monitor its use. While it’s connected to sense, it’s a detection only because of the integration.
Let’s say I move the plug (I do move them). I f I were to NOT reset everything and plugged that receptacle that was connected into a pump now into a toaster then sense would see the toaster now as the pump. Each time the toaster cane on it would be detected as the pump and send that information to the servers. That’s how smart plugs are in fact “training” Sense.
So here is what I do if moving:
I first go to Sense and disable integration. Then to Kasa and alexa and remove from both.
I reset the plug and setup in Kasa first but when it tries to reuse settings, I do t allow and make sure to use a new name (this is important). Open alexa, rediscover. Then back to Sense and turn Integration back on.
Doing this you will not lose the history from the first device (pump on my case) when moving to toaster. This will keep any bad data from going to servers.
How long or how many cycles? I don’t know. But I’d say the server store, keep and use as little or as many as are sent.
Sense does not retain the pump detection is the only thing but I already learned what I wanted to know

2 Likes

I think your approach saves the history of each short-term monitored Smartplug device, so you can go back to it over time as well and remind yourself of the waveforms ?

2 Likes